© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24592
    Prev
    Next
    INDEX
    Explanations

    loc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭĽ
    -0.27
    ponsored
    -0.25
    ç§ĥ
    -0.25
    marine
    -0.24
    Popular
    -0.24
    ponsors
    -0.24
    cki
    -0.23
    ç»ĵæŀĦæĢ§
    -0.23
    ä¸įåĥı
    -0.23
    .JSON
    -0.23
    POSITIVE LOGITS
    ague
    0.28
    ếm
    0.26
    ork
    0.25
    åį°åĪ·
    0.25
    eria
    0.24
    ç¾İåѦ
    0.24
    edic
    0.24
     Mario
    0.24
     labyrinth
    0.24
     langs
    0.23
    Activations Density 0.013%

    No Known Activations